我正在使用 Jupyter notebooks 来创建 ML Model with TuriCreate .
我遵循的步骤如上所述 .
我从https://www.kaggle.com/zynicide/wine-reviews下载了.csv和.json（同一个文件）
该文件大小为51 MB .
我创造了一个环境 turienv 来自 Anaconda Navigation 和 the following steps work perfect for smaller CSV / JSON files.
-
source激活turienv
-
pip install turicreate = 5.0
-
木星笔记本
----里面的笔记本----
import turicreate as tc
wine_data = tc.SFrame.read_json('winemag-data-130k-v2.json', orient='records')
wine_data.head() <-- I see that everything is loaded properly
wine_model = tc.text_classifier.create(wine_data,'title',features=['description'])
PROGRESS: Creating a validation set from 5 percent of training data. This may take a while.
You can set ``validation_set=None`` to disable validation tracking.
Logistic regression:
--------------------------------------------------------
Number of examples : 123481
Number of classes : 113404
Number of feature columns : 1
Number of unpacked features : 21030
Number of coefficients : 2384978493
Starting L-BFGS
--------------------------------------------------------
+-----------+----------+-----------+--------------+-------------------+---------------------+
| Iteration | Passes | Step size | Elapsed Time | Training Accuracy | Validation Accuracy |
+-----------+----------+-----------+--------------+-------------------+---------------------+
然后在大约3-4分钟内我得到错误消息msg =内核似乎已经死亡 .
谁能帮忙？我是Python的新手，而Jupyter只是我曾经使用的环境 . 如果有一个其他的env，我可以运行相同的东西，有一些指导，以便有一个更可靠的错误消息，我可以调试，请让我知道 .
Edited: 我在2018 MacBook Pro 16GB 512GB上运行上述内容 . 我在Activity Monitor Memory上看到python的容量为130GB，CPU为83％
提前致谢